Salt and Pepper Noise Removal with Multi-Class Dictionary Learning and L0 Norm Regularizations

Guo, Di; Tu, Zhangren; Wang, Jiechao; Xiao, Min; Du, Xingqiang; Qu, Xiaobo

doi:10.3390/a12010007

Cited by 5 publications

(5 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The algorithm has high image restoration power to produce restored images with a high PSNR value. Guo et al [69] have introduced a novel algorithm to enhance image sparsity to help remove salt and pepper noise removal with a fast multiclass dictionary learning, and then both the sparsity regularization and robust data fidelity are formulated as minimizations of 0 − 0 norm for impulse noise removal. Additionally, a numerical algorithm of modified alternating direction minimization is derived to solve the proposed denoising model.…”

Section: A Methodologies Of Dictionary Learning Models (Impulse Noise)mentioning

confidence: 99%

Image De-Noising With Machine Learning: A Review

et al. 2021

View full text Add to dashboard Cite

Images are susceptible to various kinds of noises, which corrupt the pictorial information stored in the images. Image de-noising has become an integral part of the image processing workflow. It is used to attenuate the noises and accentuate the specific image information stored within. Machine learning is an important tool in the image-de-noising workflow in terms of its robustness, accuracy, and time requirement. This paper explores the numerous state-of-the-art machine-learning-based image de-noisers like dictionary learning models, convolutional neural networks and generative adversarial networks for a range of noises like Gaussian, Impulse, Poisson, Mixed and Real-World noises. The motivation, algorithm and framework of different machine learning de-noisers are analyzed. These de-noisers are compared using PSNR as quality assessment metric on some benchmark datasets. The best de-noising results for different noise type is discussed along with future prospects. Among various Gaussian noise de-noisers, GCBD, BRDNet and PReLU network prove to be promising. CNN+LSTM, and MC2RNet are most suitable CNNbased Poisson de-noisers. For impulse noise removal, Blind CNN, and CNN+PSO perform well. For mixed noise removal, WDL, EM-CNN, CNN, SDL, and Mixed CNN are prominent. De-noisers like GRDN and DDFN show accurate results in the domain of real-world de-noising.

show abstract

Section: A Methodologies Of Dictionary Learning Models (Impulse Noise)mentioning

confidence: 99%

Image De-Noising With Machine Learning: A Review

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Figure 2(e) also exhibits high sparsity. We constrain this sparsity of the stripe noise using the L0-norm which describes the sparsity extremely well [ 21 , 22 ]. Therefore, the established regular term is as follows:

where d y denotes the convolution operator in the vertical direction, N n denotes stripe noises in the n th -level vertical component.…”

Section: Algorithm Compositionmentioning

confidence: 99%

An Infrared Stripe Noise Removal Method Based on Multi-Scale Wavelet Transform and Multinomial Sparse Representation

Nong

Han

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

The non-uniformity present in the infrared detector and readout circuit leads to significant stripe noises in the infrared images. The effect of these stripe noises on infrared images brings trouble to the subsequent research. The currently available algorithms for removing infrared streak noises cannot effectively protect the non-stripe information while removing the stripe noise. Compared with these algorithms, our algorithm uses a multi-scale wavelet transform to concentrate the streak noise by frequency into vertical components of different scale levels. Then, our algorithm analyzes the unique properties of the streak noise compared to the ideal vertical component. The denoising model of the vertical component at each level is established with its multinomial sparsity, and the streak noise is removed by the alternating direction method of multipliers (ADMM) algorithm for optimal calculation. To prove the usefulness of our algorithm, we carried out a large series of real experiments, comparing it with the most advanced algorithms in terms of both subjective determination and objective indices. The experimental results fully demonstrate the superiority and effectiveness of our algorithm.

show abstract

“…Sample reduction solves the enormous amount of data problem by selecting only representation samples to be the training sets [298]- [300]. Dimension reduction such as feature engineering [301]- [313], feature learning [33], [314]- [318], and feature selection [319]- [326] [151], [327]- [335].…”

Section: Curse Of Dimensionalitymentioning

confidence: 99%

“…-norm minimization (eqn. (1.2)) has been successfully used for background subtraction[153] and viewpoint classification for anomaly detection[5], signal denoising and error correction[147]-[151], superresolution reconstruction[152],[420], background subtraction[153] and dictionary learning[153]. Similar to the works in[4], the theoretical workpresented has shown that the -norm minimization (eqn.…”

mentioning

confidence: 93%

See 1 more Smart Citation

Novel techniques for sparse representation problems

Chai¹

View full text Add to dashboard Cite

This thesis contains material from papers published in the following peer-reviewed conferences and publication drafts under preparation for the publications in the following peer-reviewed journals where I was the first and corresponding author. Chapter 3 is prepared as W.H. Chai, and C. Quek. A novel Quasi-Newton Technique for Composite Convex Minimization. Pattern Recognition (Under revision) The contributions of the co-authors are as follows:  I defined the initial project direction  Assoc Prof Quek edited the manuscript drafts.  The manuscript was revised by Assoc Prof Quek.  I generated the idea, derived the theory, designed the study and the algorithm, performed all the experimental works, and analyzed the results at the School of Computer Science and Rolls-Royce@NTU Corporate Lab. Chapter 4 is prepared as W.H. Chai, and C. Quek. Representation Recovery via -norm Minimization with Corrupted Data. Information Sciences (Submitted)The contributions of the co-authors are as follows: Assoc Prof Quek provided the initial project direction and edited the manuscript drafts. The manuscript was revised by Assoc Prof Quek. I generated the idea, derived the theory, designed the study and the algorithm, performed all the experimental works, and analyzed the results at the School of Computer Science and Rolls-Royce@NTU Corporate Lab.Chapter 5 is prepared as W.H. Chai, and C. Quek. Feature Selection for Dictionary Transfer. Pattern Recognition Letters (Under preparation for publication)The contributions of the co-authors are as follows:x  I defined the initial project direction  Assoc Prof Quek edited the manuscript drafts. The manuscript was revised by Assoc Prof Quek. I generated the idea, derived the theory, designed the study and the algorithm, performed all the experimental works, and analyzed the results at the School of Computer Science and Rolls-Royce@NTU Corporate Lab.

show abstract

Salt and Pepper Noise Removal with Multi-Class Dictionary Learning and L0 Norm Regularizations

Cited by 5 publications

References 38 publications

Image De-Noising With Machine Learning: A Review

Image De-Noising With Machine Learning: A Review

An Infrared Stripe Noise Removal Method Based on Multi-Scale Wavelet Transform and Multinomial Sparse Representation

Novel techniques for sparse representation problems

Contact Info

Product

Resources

About